Smelting industry knowledge graph management method and system

Abstract

The invention discloses a smelting industry knowledge graph management method and system, and relates to the technical field of the smelting industry. Historical smelting records are analyzed, a plurality of smelting condition analysis data sets including smelting process performance factors and condition interpretation data are extracted, a semantic analysis technology is adopted, condition keywords and interpretation keywords are extracted from the data sets, and the smelting process performance factors and the condition interpretation data are analyzed; determining a semantic relationship between the condition parameters and the interpretation keywords; constructing a knowledge graph index structure based on the condition keywords and the parameters, associating the interpretation data, and classifying the index structure and branches according to the equivalence of the interpretation keywords; analyzing an expandable range of condition parameters in the same category of index branches, and determining fuzzy features; according to the method, the problems of smelting data unstructuring, knowledge association missing and insufficient dynamic fuzzy management are effectively solved, the practicability and adaptability of the knowledge graph are improved, and smelting process optimization and intelligent decision making are supported.

Description

Technical Field

[0001] The present invention relates to the technical field of smelting industry, and in particular to a knowledge graph management method and system for smelting industry. Background Art

[0002] As an important part of the modern industrial system, the smelting industry involves complex physical and chemical reactions and multivariable control in its production process. The large amount of historical records generated (such as workload data, process parameters, status descriptions, etc.) contain rich empirical knowledge. However, the traditional smelting data management methods are mainly based on manual records or simple database storage. The data presents unstructured or semi-structured characteristics and is difficult to be directly used for systematic analysis and knowledge mining. At the same time, there is a lack of effective association mechanism between the various performance factors involved in the smelting process (such as temperature, pressure, output fluctuations) and status interpretation (such as equipment failures, process optimization suggestions), which makes it difficult to fully utilize the implicit laws and experience. In addition, the smelting industry has significant dynamic characteristics, and the workload and process parameters often fluctuate over time, showing a certain degree of ambiguity and uncertainty. When dealing with these dynamic changes, existing technologies often lack scientific quantitative methods and scalable knowledge representation frameworks. This makes it difficult for smelting companies to achieve efficient process optimization and intelligent decision support based on historical data. Summary of the invention

[0003] The purpose of the present invention is to provide a management method and system capable of generating a knowledge graph for the smelting industry.

[0004] The present invention discloses a method for managing a knowledge graph of a smelting industry, comprising: Step S100, analyzing historical smelting records to determine a number of smelting status analysis data groups, the smelting status analysis data groups including a number of smelting process performance factors and status interpretation data; Step S200, using semantic analysis technology, extracting condition keywords and interpretation keywords from the smelting condition analysis data group, determining condition parameters corresponding to the condition keywords, and determining the semantic pointing relationship of the interpretation keywords; Step S300, based on the condition keywords and corresponding condition parameters of the smelting condition analysis data group, construct an index structure of the industrial knowledge graph, associate the index structure with the corresponding condition interpretation data, classify the index structure based on the equality of the interpretation keywords of the smelting condition analysis data group, and classify the index branches of the index structure; Step S400, determining the expandable range of each status parameter of the same category of index branches, and then determining the fuzzy features of the index branches.

[0005] In some embodiments disclosed in the present invention, the method for determining a plurality of smelting condition analysis data groups includes: Step S101, determining the change of smelting workload in the time dimension in the historical smelting records, and constructing a plurality of smelting workload curves, and classifying each smelting workload curve by similarity to obtain a plurality of smelting workload curve groups; Step S102, based on each smelting work curve group, the corresponding historical smelting records are truncated and classified to obtain several historical smelting record segment groups, and semantic analysis is performed on the historical smelting record segments in each historical smelting record segment group, and the smelting process performance description segments and the status interpretation description segments are marked respectively, and the smelting process performance description segments belonging to the same description type are associated and recorded as smelting process performance factors, and the status interpretation description segments are recorded as status interpretation data.

[0006] In some embodiments disclosed in the present invention, the method for similarity classification of each smelting working curve includes: Step S1011, an upper workload comparison line and a lower workload comparison line are set for each smelting workload curve. If the smelting workload curve is higher than the upper workload comparison line, the corresponding curve segment is intercepted and recorded as the upper curve segment. If the smelting workload curve is lower than the lower workload comparison line, the corresponding curve segment is intercepted and recorded as the lower curve segment. The upper curve segment length of each upper curve segment and the lower curve length of the lower curve segment are determined, and the upper curve segment interval between the upper curve segments and the lower curve segment interval between the lower curve segments are determined, and the curve peak value of the upper curve segment and the curve minimum value of the lower curve segment are determined; Step S1012, constructing a curve segment parameter group sequence according to the order in which the upper curve segment and the lower curve segment appear, wherein the curve segment parameter group is divided into an upper curve segment parameter group and a lower curve segment parameter group, wherein the upper curve segment parameter group includes an upper curve segment length, an upper curve segment interval, and a curve peak value, and the lower curve segment parameter group includes a lower curve segment length, a lower curve segment interval, and a curve minimum value; Step S1013, comparing the curve segment parameter group sequences with each other. During each comparison, the curve segment parameter group sequences are randomly displaced, and the initial similarity between them is determined. The highest initial similarity is selected as the reference similarity between the curve segment parameter group sequences. Step S1014, classifying the smelting working curves corresponding to the curve segment parameter group sequence with a reference similarity greater than or equal to a preset value.

[0007] In some embodiments disclosed in the present invention, the method for determining the initial similarity degree includes: Step S10131, align the curve segment parameter group sequence, compare the difference features between each curve parameter group in the sequence, the difference features include the difference in upper curve segment length, the difference in lower curve segment length, the difference in upper curve segment interval, the difference in lower curve segment interval, the difference in curve peak value and the difference in curve minimum value, and determine the initial similarity based on the continuous performance of the difference features of all curve parameter groups.

[0008] In some embodiments disclosed in the present invention, a method for constructing an index structure of an industrial knowledge graph based on condition keywords and corresponding condition parameters of a smelting condition analysis data set includes: Step S301, comparing the determined situation keywords with the preset word order template, determining the connection sequence relationship between the situation keywords, and using the situation keywords as index relationship nodes for relationship connection; Step S302, setting an index relationship node for the synonym of the condition keyword, and performing parallel expansion connection with the index relationship node corresponding to the condition keyword to form a synonym relationship node cluster, and connecting the synonym relationship node cluster with other sequential index relationship nodes; Step S303, configure the status parameters to the corresponding index relationship nodes or synonymous relationship node clusters to form an index structure of the industrial data graph.

[0009] In some embodiments disclosed herein, a method for determining the equivalence of interpretation keywords of a smelting condition analysis data set includes: Step S304, summing the total number of all interpretation keywords between the smelting condition analysis data groups, determining the corresponding number of keywords of the corresponding interpretation keywords, and calculating the corresponding keyword ratio between the number of corresponding keywords and the total number of keywords; Step S305, determining whether the semantic orientations of the corresponding interpretation keywords between the smelting condition analysis data groups are identical, and determining the ratio of the number of identical semantic orientations to the number of identical semantic orientations; Step S306, based on the corresponding keyword ratio and equivalent semantic pointing ratio of the smelting condition analysis data group, determine the degree of similarity of the interpretation keywords between the smelting condition analysis data groups. If the degree of similarity is greater than or equal to the preset value, it is determined that there is an equivalent relationship between the interpretation keywords between the smelting analysis data groups.

[0010] In some embodiments disclosed in the present invention, a method for determining an expandable range of each status parameter of an index branch of the same category includes: Step S401, construct a status parameter reference axis for the status parameter, and map the same type of status parameters to the status parameter reference axis in the form of parameter mapping points, determine the ratio of parameter mapping points near each parameter mapping point, and based on the ratio of parameter mapping points near each parameter mapping point, determine the status parameter extension range corresponding to the parameter mapping point, wherein the parameter mapping point ratio is the ratio of the number of parameter mapping points in the range near the parameter mapping point to the number of all parameter mapping points on the status parameter reference axis.

[0011] In some embodiments disclosed in the present invention, a method for determining an extended range of a status parameter corresponding to a parameter mapping point includes: Step S4011, set several levels of range segments near the parameter mapping point, each range segment is set with a comparison mapping point ratio, and compare the parameter mapping point ratio with the comparison mapping point ratio in sequence. If the parameter mapping point ratio is greater than or equal to the comparison mapping point ratio, compare the size relationship between the parameter mapping point ratio and the comparison mapping point ratio of the next range segment, until the parameter mapping point ratio is less than the comparison mapping point ratio, then the range segment at this time is identified as the extended range of the parameter mapping point.

[0012] In some embodiments disclosed in the present invention, a smelting industry knowledge graph management system is also disclosed, including: The first module is used to analyze the historical smelting records and determine a number of smelting status analysis data groups, which include a number of smelting process performance factors and status interpretation data; The second module is used to extract condition keywords and interpretation keywords from the smelting condition analysis data group using semantic analysis technology, determine the condition parameters corresponding to the condition keywords, and determine the semantic pointing relationship of the interpretation keywords; The third module is used to construct an index structure of the industrial knowledge graph based on the condition keywords and corresponding condition parameters of the smelting condition analysis data group, associate the index structure with the corresponding condition interpretation data, classify the index structure based on the equality of the interpretation keywords of the smelting condition analysis data group, and classify the index branches of the index structure; The fourth module is used to determine the expandable range of each status parameter of the index branch of the same category, and then determine the fuzzy characteristics of the index branch.

[0013] The present invention discloses a knowledge graph management method and system for the smelting industry, which relates to the technical field of the smelting industry, analyzes historical smelting records, extracts a number of smelting status analysis data groups, including smelting process performance factors and status interpretation data, and uses semantic analysis technology to extract status keywords and interpretation keywords from the data group, and determine the semantic relationship between status parameters and interpretation keywords; constructs a knowledge graph index structure based on status keywords and parameters, associates interpretation data, and classifies index structures and branches according to the equivalence of interpretation keywords; analyzes the expandable range of status parameters in the same category index branches, and determines fuzzy features; the present invention effectively solves the problems of unstructured smelting data, lack of knowledge association, and insufficient dynamic fuzzy management, improves the practicality and adaptability of knowledge graphs, and supports smelting process optimization and intelligent decision-making.

[0014] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a method step diagram of the smelting industry knowledge graph management method disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0017] The following will be combined with the accompanying drawings and specific embodiments to clearly and completely describe the technical solution of the present invention. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and cannot be understood as limiting the scope of protection of the present invention. Those skilled in the art in this field can make some non-essential improvements and adjustments based on the content of the present invention described below. In the present invention, unless otherwise clearly specified and limited, the technical terms used in the present invention should be the common meanings understood by the technical personnel described in the present invention.

[0018] Embodiment:

[0019] The present invention discloses a method for managing a knowledge graph of a smelting industry, see Figure 1 ,include: Step S100, analyzing historical smelting records to determine a number of smelting status analysis data groups, the smelting status analysis data groups including a number of smelting process performance factors and status interpretation data.

[0020] In the smelting industry, historical records usually exist in the form of logs, reports or equipment monitoring data. These data are often unstructured or semi-structured, containing a large amount of text descriptions, numerical records and time series information. The goal of step S100 is to transform these scattered data into structured "smelting status analysis data groups" through systematic analysis methods, providing basic materials for the subsequent knowledge graph construction. Its core principle is based on data mining and information extraction technology. First, the historical records need to be preprocessed, such as removing noise data and unifying the format, and then identifying key information through statistical analysis or pattern recognition methods. Specifically, the analysis process will focus on two main outputs: one is "smelting process performance factors", which are key indicators extracted from the records that reflect the state of the smelting process, which may include quantitative data such as temperature, pressure, and output rate, or qualitative descriptions such as "slag accumulation" and "equipment vibration"; the second is "status interpretation data", which is explanatory information on performance factors, such as "high temperature leads to reduced furnace efficiency" or "pressure abnormality due to pipeline blockage" and other diagnostic conclusions. Technical means to achieve this step may include entity recognition in natural language processing (NLP) for extracting factors from text, and time series analysis for mining trends and anomalies from numerical data. In addition, in order to ensure the validity of the data group, it may be necessary to set screening criteria, such as data completeness or representativeness, to divide the massive records into several representative subsets. The logic of this division is similar to feature engineering in machine learning, which abstracts the original data into more easily processable information units through dimensionality reduction and clustering methods. The principle of the whole process is to extract structured knowledge fragments from complex industrial data, lay the foundation for subsequent semantic analysis and graph construction, and ultimately achieve the transformation from "data" to "information".

[0021] Step S200, using semantic analysis technology, extracting condition keywords and interpretation keywords from the smelting condition analysis data group, determining the condition parameters corresponding to the condition keywords, and determining the semantic pointing relationship of the interpretation keywords.

[0022] Step S200 is the core link of deep semantic analysis of the smelting condition analysis data group generated by S100. Its principle is based on natural language processing (NLP) and semantic network construction. This process aims to further extract key semantic elements from structured data and establish associations between them, providing a semantic basis for the construction of knowledge graphs. First, semantic analysis techniques (such as word frequency statistics, word segmentation, and dependency syntax analysis) are used to process the "smelting process performance factors" and "condition interpretation data" in the data group, and two types of keywords are extracted: one is "condition keywords", such as "high temperature", "blockage", and "melt flow rate". These words directly reflect the core status or problems in the smelting process. Through context analysis, their corresponding "condition parameters" can be further determined, such as the specific temperature value associated with "high temperature" (such as 1350°C) or the pressure difference corresponding to "blockage" (such as 0.5MPa); the second is "interpretation keywords", such as "overheating causes" and "efficiency reduction". These words are extracted from the condition interpretation data and are used to describe the causes or results behind the status. After extracting keywords, the technical focus shifts to determining semantic relationships, which requires the use of word vector models (such as Word2Vec) or knowledge graph embedding technology (such as TransE) to analyze and interpret the semantic pointing relationship between keywords and condition keywords, such as "cause of overheating" pointing to "equipment aging" or "efficiency reduction" pointing to "high temperature". The principle of this process is to convert discrete text information into a computable structured relationship network through semantic similarity and syntactic dependency. In addition, in order to improve accuracy, it may be necessary to correct and supplement the extraction results in combination with domain dictionaries or expert knowledge. The implementation of the entire step relies on information extraction and relationship extraction technology in NLP, which aims to make implicit knowledge in the data group explicit, provide semantic support for subsequent graph index structures, and ultimately achieve the transition from "information" to "knowledge".

[0023] Step S300, based on the condition keywords and corresponding condition parameters of the smelting condition analysis data group, construct an index structure of the industrial knowledge graph, and associate the index structure with the corresponding condition interpretation data, classify the index structure based on the equality of the interpretation keywords of the smelting condition analysis data group, and classify the index branches of the index structure.

[0024] Step S300 is the core link of constructing the knowledge graph of the smelting industry. Its principle is based on graph theory and semantic clustering technology in knowledge representation, and aims to organize the semantic elements extracted by S200 into a hierarchical and queryable knowledge system. Specifically, the index structure of the graph is first constructed based on the "condition keywords" and their corresponding "condition parameters". This process regards keywords as nodes and parameters as attributes of nodes. The nodes are connected into a network through semantic relationships (such as cause and effect, time sequence), such as "high temperature (1350°C)" is connected to "efficiency reduction" to form a basic relationship graph. At the same time, the index structure will be associated with the corresponding "condition interpretation data", such as "the reason for the decline in efficiency due to high temperature is equipment aging". These interpretation data are mounted on nodes or edges as supplementary information to enhance the explanatory power of the graph. After the construction is completed, the optimization and classification of the graph become the key. The index structure is sorted by "interpreting the equivalence of keywords". This requires semantic similarity analysis (such as cosine similarity) to determine the overlap of meanings between keywords. For example, "overheating" and "high temperature" may be identified as equivalent, so that related nodes are clustered into one category. The principle of this classification is similar to clustering algorithms (such as K-means), which improves the simplicity of the graph by reducing redundancy. In addition, the "index branch" (i.e., the subgraph structure in the graph) is further classified, which may be based on the process stage (such as smelting, refining) or the type of problem (such as equipment failure, process abnormality) to form a hierarchical index system. The implementation of the entire step depends on the storage and query capabilities of the graph database (such as Neo4j) and the classification technology in semantic analysis, ensuring that the graph can not only reflect the complex relationship of the smelting process, but also facilitate rapid retrieval and expansion, and ultimately achieve a leap from "knowledge" to "system".

[0025] Step S400, determining the expandable range of each status parameter of the same category of index branches, and then determining the fuzzy features of the index branches.

[0026] Step S400 is a key link in the dynamic and uncertainty management of the knowledge graph. Its principle combines statistical analysis and fuzzy logic, aiming to enhance the adaptability of the graph to the complexity of the smelting process. In S300, the index branches of the graph have been classified by category, and each branch contains several state parameters (such as temperature and pressure values), which are often not fixed in actual industrial scenarios, but show a certain range of fluctuations over time or conditions. Therefore, this step first analyzes each state parameter in the same category branch through statistical methods, such as fitting the distribution of "temperature" in historical data to determine its "expandable range", such as 1350°C±50°C, which reflects the possible change boundary of the parameter. To achieve this process, it may be necessary to use a probability distribution model (such as normal distribution) or interval estimation technology to ensure that the range is statistically significant. Next, "fuzzy features" are further extracted based on these ranges, which is achieved through fuzzy mathematics. For example, the temperature is divided into fuzzy states such as "normal", "high", and "too high", and the probability of each state is quantified with a membership function (such as "1350°C is too high with a membership of 0.8"). The principle of this fuzzification is to recognize the uncertainty in the smelting process and convert it into computable features, so that the map not only describes static facts, but also reflects dynamic trends. The implementation of the entire step may combine data visualization (such as drawing parameter distribution maps) and fuzzy reasoning systems to ultimately generate a fuzzy feature description for each index branch, such as "the fuzzy feature of the high temperature branch is an 80% probability of high temperature." Through this process, the map evolves from a static knowledge network to a dynamic decision support tool, significantly improving its flexibility and practicality in practical applications.

[0027] In some embodiments disclosed in the present invention, the method for determining a plurality of smelting condition analysis data groups includes: Step S101, determining the change of smelting workload in the time dimension in the historical smelting records, constructing a plurality of smelting workload curves, and classifying each smelting workload curve by similarity to obtain a plurality of smelting workload curve groups.

[0028] The purpose of step S101 is to extract the workload change characteristics in the time dimension from the historical smelting records, and classify them through similarity analysis to provide a data basis for subsequent situation analysis. Its principle is based on time series analysis and clustering technology, aiming to mine regular patterns from complex industrial data. Specifically, it is first necessary to extract the key indicator of "smelting workload" from historical records. The workload may be output (such as tons per hour), energy consumption (such as electricity consumption) or equipment operating load (such as speed). These data are usually recorded in the form of timestamps to form a continuous or discrete time series. The process of determining workload changes involves data cleaning (such as filling missing values, smoothing noise) and feature extraction (such as calculating trends, periodicity), and then these time series are converted into visual "smelting workload curves", each of which represents the dynamic changes in workload over a period of time.

[0029] Step S102, based on each smelting work curve group, the corresponding historical smelting records are truncated and classified to obtain several historical smelting record segment groups, and semantic analysis is performed on the historical smelting record segments in each historical smelting record segment group, and the smelting process performance description segments and the status interpretation description segments are marked respectively, and the smelting process performance description segments belonging to the same description type are associated and recorded as smelting process performance factors, and the status interpretation description segments are recorded as status interpretation data.

[0030] Step S102 is to further process the smelting work curve group generated by S101, with the goal of segmenting the historical records according to the curve characteristics and extracting key information, and finally forming a structured "smelting status analysis data group". Its principle combines time series segmentation and natural language processing (NLP) technology, aiming to mine the semantic content of process performance and interpretation from the data. Specifically, firstly, based on the characteristics of each smelting work curve group (such as the time span or change trend of the curve), the corresponding historical smelting records are truncated by time period. For example, a curve showing "increase in workload-stable" may correspond to a record of a certain day, and this record is intercepted as an independent segment. In this way, the original records are divided into several "historical smelting record segment groups", each segment group corresponds to a work curve group, and the correlation in the time dimension is retained. Next, semantic analysis is performed on the record segments in each segment group. This process relies on NLP technology (such as named entity recognition and syntactic analysis) to identify and mark two types of text fragments: one is the "segment describing the performance of the smelting process", such as "the temperature rises to 1400°C" or "the slag accumulation is obvious", which reflects the process status; the other is the "segment describing the interpretation of the status", such as "the efficiency is reduced due to excessive temperature" or "the accumulation is due to insufficient cooling", which provides an explanation or reason for the status. In order to structure this information, it is necessary to associate the performance description segments of the same type, for example, all descriptions that mention "temperature" are classified into one category and recorded as "smelting process performance factor" (such as "high temperature factor"), while the interpretation description segment is directly marked as "status interpretation data" (such as "overheating cause").

[0031] In some embodiments disclosed in the present invention, the method for similarity classification of each smelting working curve includes: Step S1011, an upper workload comparison line and a lower workload comparison line are set for each smelting workload curve. If the smelting workload curve is higher than the upper workload comparison line, the corresponding curve segment is intercepted and recorded as the upper curve segment. If the smelting workload curve is lower than the lower workload comparison line, the corresponding curve segment is intercepted and recorded as the lower curve segment. The upper curve segment length of each upper curve segment and the lower curve length of the lower curve segment are determined, and the upper curve segment interval between the upper curve segments and the lower curve segment interval between the lower curve segments are determined. The peak value of the upper curve segment and the minimum value of the lower curve segment are determined.

[0032] Step S1012, construct a curve segment parameter group sequence according to the order in which the upper curve segment and the lower curve segment appear, and the curve segment parameter group is divided into an upper curve segment parameter group and a lower curve segment parameter group. The upper curve segment parameter group includes the upper curve segment length, the upper curve segment interval and the curve peak value, and the lower curve segment parameter group includes the lower curve segment length, the lower curve segment interval and the curve minimum value.

[0033] Step S1013, compare the curve segment parameter group sequences with each other. During each comparison, the curve segment parameter group sequences are randomly displaced, and the initial similarity between them is determined. The highest initial similarity is selected as the reference similarity between the curve segment parameter group sequences.

[0034] Step S1014, classifying the smelting working curves corresponding to the curve segment parameter group sequence with a reference similarity greater than or equal to a preset value.

[0035] In some embodiments disclosed in the present invention, the method for determining the initial similarity degree includes: Step S10131, align the curve segment parameter group sequence, compare the difference features between each curve parameter group in the sequence, the difference features include the difference in upper curve segment length, the difference in lower curve segment length, the difference in upper curve segment interval, the difference in lower curve segment interval, the difference in curve peak value and the difference in curve minimum value, and determine the initial similarity based on the continuous performance of the difference features of all curve parameter groups.

[0036] Among them, the expression for calculating the initial similarity is: .

[0037] Among them, S is the initial similarity, It is a continuous performance determination function used to determine whether the difference characteristics of the i-th curve segment parameter group in the curve segment parameter group sequence are the same as those of the adjacent curve segment parameter groups. The determination method includes calculating the sub-similarity between the i-th curve segment parameter groups. If the sub-similarity is greater than or equal to a preset value, the i-th curve segment parameter groups are considered to be similar. If the (i-1)th curve segment parameter groups are similar, or the (i+1)th curve segment parameter groups are similar, then Output 1, otherwise output 0, L is the continuous performance impact adjustment coefficient, C is the continuous performance impact adjustment constant; Among them, the expression for calculating the sub-similarity between the i-th curve segment parameter groups is: .

[0038] in, is the sub-similarity between the i-th curve segment parameter group, is the preset maximum curve segment length difference, is the difference in the length of the curve segment, is the preset maximum curve segment interval difference, is the difference between curve segments, The preset maximum curve peak value difference or the maximum curve minimum value difference, is the difference in the peak value of the curve or the difference in the minimum value of the curve, is the adjustment coefficient of the difference in the length of the curve segment, is the adjustment coefficient of the difference effect on the curve segment interval, and b is the adjustment constant of the difference effect.

[0039] In some embodiments disclosed in the present invention, a method for constructing an index structure of an industrial knowledge graph based on condition keywords and corresponding condition parameters of a smelting condition analysis data set includes: Step S301 : compare the determined situation keywords with the preset word order template, determine the connection sequence relationship between the situation keywords, and use the situation keywords as index relationship nodes for relationship connection.

[0040] Step S302, setting index relationship nodes for synonyms of the situation keywords, and performing parallel extension connection with the index relationship nodes corresponding to the situation keywords to form a synonym relationship node cluster, and connecting the synonym relationship node cluster with other sequential index relationship nodes.

[0041] Step S303, configure the status parameters to the corresponding index relationship nodes or synonymous relationship node clusters to form an index structure of the industrial data graph.

[0042] In some embodiments disclosed herein, a method for determining the equivalence of interpretation keywords of a smelting condition analysis data set includes: Step S304, summing up the total number of all interpretation keywords between the smelting condition analysis data groups, determining the corresponding keyword quantity of the corresponding interpretation keywords, and calculating the corresponding keyword ratio between the corresponding keyword quantity and the total number of keywords.

[0043] Step S305, determining whether the semantic orientations of the corresponding interpretation keywords between the smelting condition analysis data groups are identical, and determining the ratio of the number of identical semantic orientations to the number of all semantic orientations.

[0044] Step S306, based on the corresponding keyword ratio and equivalent semantic pointing ratio of the smelting condition analysis data group, determine the degree of similarity of the interpretation keywords between the smelting condition analysis data groups. If the degree of similarity is greater than or equal to the preset value, it is determined that there is an equivalent relationship between the interpretation keywords between the smelting analysis data groups.

[0045] The expression for calculating the degree of equality is: .

[0046] Among them, D is the degree of equality, is the corresponding keyword ratio, For equivalent semantics pointing to the ratio, is the weight coefficient equivalent to the corresponding keyword ratio, The equivalent semantics points to the proportional equivalent weight coefficient.

[0047] In some embodiments disclosed in the present invention, a method for determining an expandable range of each status parameter of an index branch of the same category includes: Step S401, construct a status parameter reference axis for the status parameter, and map the same type of status parameters to the status parameter reference axis in the form of parameter mapping points, determine the ratio of parameter mapping points near each parameter mapping point, and based on the ratio of parameter mapping points near each parameter mapping point, determine the status parameter extension range corresponding to the parameter mapping point, wherein the parameter mapping point ratio is the ratio of the number of parameter mapping points in the range near the parameter mapping point to the number of all parameter mapping points on the status parameter reference axis.

[0048] The purpose of step S401 is to determine the expandable range of the condition parameters (such as temperature and pressure) in the same category index branch to quantify the dynamic changes and uncertainties of these parameters in the smelting process. Its principle integrates the ideas of statistical analysis, data visualization and spatial distribution, and provides a basis for subsequent fuzzy feature extraction. Specifically, first, a "condition parameter reference axis" is constructed for a certain type of condition parameter (such as "temperature"). This is an abstract numerical axis, similar to a one-dimensional coordinate system, and the range covers the minimum value to the maximum value that the parameter may appear (for example, the temperature axis may be 0°C to 2000°C). The construction of this reference axis is based on historical data statistics, and the upper and lower limits may be determined by analyzing the distribution of the parameter in all relevant records. Next, the same type of condition parameters (for example, multiple temperature values ​​recorded in a certain category branch, such as 1350°C, 1370°C, 1340°C) are projected onto the reference axis in the form of "parameter mapping points", and each mapping point corresponds to a specific value, forming a distribution point set. This process is similar to scatter plotting in data visualization, which aims to convert discrete parameter values ​​into spatial representations.

[0049] In some embodiments disclosed in the present invention, a method for determining an extended range of a status parameter corresponding to a parameter mapping point includes: Step S4011, set several levels of range segments near the parameter mapping point, each range segment is set with a comparison mapping point ratio, and compare the parameter mapping point ratio with the comparison mapping point ratio in sequence. If the parameter mapping point ratio is greater than or equal to the comparison mapping point ratio, compare the size relationship between the parameter mapping point ratio and the comparison mapping point ratio of the next range segment, until the parameter mapping point ratio is less than the comparison mapping point ratio, then the range segment at this time is identified as the extended range of the parameter mapping point.

[0050] In some embodiments disclosed in the present invention, a smelting industry knowledge graph management system is also disclosed, including: The first module is used to analyze the historical smelting records and determine a number of smelting status analysis data groups, which include a number of smelting process performance factors and status interpretation data; The second module is used to extract condition keywords and interpretation keywords from the smelting condition analysis data group using semantic analysis technology, determine the condition parameters corresponding to the condition keywords, and determine the semantic pointing relationship of the interpretation keywords; The third module is used to construct an index structure of the industrial knowledge graph based on the condition keywords and corresponding condition parameters of the smelting condition analysis data group, associate the index structure with the corresponding condition interpretation data, classify the index structure based on the equality of the interpretation keywords of the smelting condition analysis data group, and classify the index branches of the index structure; The fourth module is used to determine the expandable range of each status parameter of the index branch of the same category, and then determine the fuzzy characteristics of the index branch.

[0051] The present invention discloses a knowledge graph management method and system for the smelting industry, which relates to the technical field of the smelting industry, analyzes historical smelting records, extracts a number of smelting status analysis data groups, including smelting process performance factors and status interpretation data, and uses semantic analysis technology to extract status keywords and interpretation keywords from the data group, and determine the semantic relationship between status parameters and interpretation keywords; constructs a knowledge graph index structure based on status keywords and parameters, associates interpretation data, and classifies index structures and branches according to the equivalence of interpretation keywords; analyzes the expandable range of status parameters in the same category index branches, and determines fuzzy features; the present invention effectively solves the problems of unstructured smelting data, lack of knowledge association, and insufficient dynamic fuzzy management, improves the practicality and adaptability of knowledge graphs, and supports smelting process optimization and intelligent decision-making.

[0052] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0053] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A knowledge graph management method for the smelting industry, characterized in that: include: Step S100, analyzing historical smelting records to determine a number of smelting status analysis data groups, the smelting status analysis data groups including a number of smelting process performance factors and status interpretation data; Step S200, using semantic analysis technology, extracting condition keywords and interpretation keywords from the smelting condition analysis data group, determining condition parameters corresponding to the condition keywords, and determining the semantic pointing relationship of the interpretation keywords; Step S300, based on the condition keywords and corresponding condition parameters of the smelting condition analysis data group, construct an index structure of the industrial knowledge graph, associate the index structure with the corresponding condition interpretation data, classify the index structure based on the equality of the interpretation keywords of the smelting condition analysis data group, and classify the index branches of the index structure; Step S400, determining the expandable range of each status parameter of the same category of index branches, and then determining the fuzzy features of the index branches.

2. The method for managing knowledge graphs for smelting industry according to claim 1, characterized in that: Methods for determining a number of metallurgical condition analysis data sets include: Step S101, determining the change of smelting workload in the time dimension in the historical smelting records, and constructing a plurality of smelting workload curves, and classifying each smelting workload curve by similarity to obtain a plurality of smelting workload curve groups; Step S102, based on each smelting work curve group, the corresponding historical smelting records are truncated and classified to obtain several historical smelting record segment groups, and semantic analysis is performed on the historical smelting record segments in each historical smelting record segment group, and the smelting process performance description segments and the status interpretation description segments are marked respectively, and the smelting process performance description segments belonging to the same description type are associated and recorded as smelting process performance factors, and the status interpretation description segments are recorded as status interpretation data.

3. The smelting industry knowledge graph management method according to claim 2 is characterized in that: The methods for similarity classification of each smelting working curve include: Step S1011, an upper workload comparison line and a lower workload comparison line are set for each smelting workload curve. If the smelting workload curve is higher than the upper workload comparison line, the corresponding curve segment is intercepted and recorded as the upper curve segment. If the smelting workload curve is lower than the lower workload comparison line, the corresponding curve segment is intercepted and recorded as the lower curve segment. The upper curve segment length of each upper curve segment and the lower curve length of the lower curve segment are determined, and the upper curve segment interval between the upper curve segments and the lower curve segment interval between the lower curve segments are determined, and the curve peak value of the upper curve segment and the curve minimum value of the lower curve segment are determined; Step S1012, constructing a curve segment parameter group sequence according to the order in which the upper curve segment and the lower curve segment appear, wherein the curve segment parameter group is divided into an upper curve segment parameter group and a lower curve segment parameter group, wherein the upper curve segment parameter group includes an upper curve segment length, an upper curve segment interval, and a curve peak value, and the lower curve segment parameter group includes a lower curve segment length, a lower curve segment interval, and a curve minimum value; Step S1013, comparing the curve segment parameter group sequences with each other. During each comparison, the curve segment parameter group sequences are randomly displaced, and the initial similarity between them is determined. The highest initial similarity is selected as the reference similarity between the curve segment parameter group sequences. Step S1014, classifying the smelting working curves corresponding to the curve segment parameter group sequence with a reference similarity greater than or equal to a preset value.

4. The method for managing knowledge graphs for smelting industry according to claim 3, characterized in that: Methods for determining the initial degree of similarity include: Step S10131, align the curve segment parameter group sequence, compare the difference features between each curve parameter group in the sequence, the difference features include the difference in upper curve segment length, the difference in lower curve segment length, the difference in upper curve segment interval, the difference in lower curve segment interval, the difference in curve peak value and the difference in curve minimum value, and determine the initial similarity based on the continuous performance of the difference features of all curve parameter groups.

5. The method for managing knowledge graphs for smelting industry according to claim 1, characterized in that: Based on the condition keywords and corresponding condition parameters of the smelting condition analysis data set, the method for constructing the index structure of the industrial knowledge graph includes: Step S301, comparing the determined situation keywords with the preset word order template, determining the connection sequence relationship between the situation keywords, and using the situation keywords as index relationship nodes for relationship connection; Step S302, setting an index relationship node for the synonym of the condition keyword, and performing parallel expansion connection with the index relationship node corresponding to the condition keyword to form a synonym relationship node cluster, and connecting the synonym relationship node cluster with other sequential index relationship nodes; Step S303, configure the status parameters to the corresponding index relationship nodes or synonymous relationship node clusters to form an index structure of the industrial data graph.

6. The method for managing knowledge graphs for smelting industry according to claim 1, characterized in that: Methods for determining equivalence of interpretation keywords for a metallurgical analysis data set include: Step S304, summing the total number of all interpretation keywords between the smelting condition analysis data groups, determining the corresponding number of keywords of the corresponding interpretation keywords, and calculating the corresponding keyword ratio between the number of corresponding keywords and the total number of keywords; Step S305, determining whether the semantic orientations of the corresponding interpretation keywords between the smelting condition analysis data groups are identical, and determining the ratio of the number of identical semantic orientations to the number of identical semantic orientations; Step S306, based on the corresponding keyword ratio and equivalent semantic pointing ratio of the smelting condition analysis data group, determine the degree of similarity of the interpretation keywords between the smelting condition analysis data groups. If the degree of similarity is greater than or equal to the preset value, it is determined that there is an equivalent relationship between the interpretation keywords between the smelting analysis data groups.

7. The method for managing knowledge graphs for smelting industry according to claim 1, characterized in that: The method for determining the expandable range of each status parameter of the same category of index branches includes: Step S401, construct a status parameter reference axis for the status parameter, and map the same type of status parameters to the status parameter reference axis in the form of parameter mapping points, determine the ratio of parameter mapping points near each parameter mapping point, and based on the ratio of parameter mapping points near each parameter mapping point, determine the status parameter extension range corresponding to the parameter mapping point, wherein the parameter mapping point ratio is the ratio of the number of parameter mapping points in the range near the parameter mapping point to the number of all parameter mapping points on the status parameter reference axis.

8. The method for managing knowledge graphs for smelting industry according to claim 7, characterized in that: The method for determining the extended range of the status parameter corresponding to the parameter mapping point includes: Step S4011, set several levels of range segments near the parameter mapping point, each range segment is set with a comparison mapping point ratio, and compare the parameter mapping point ratio with the comparison mapping point ratio in sequence. If the parameter mapping point ratio is greater than or equal to the comparison mapping point ratio, compare the size relationship between the parameter mapping point ratio and the comparison mapping point ratio of the next range segment, until the parameter mapping point ratio is less than the comparison mapping point ratio, then the range segment at this time is identified as the extended range of the parameter mapping point.

9. The knowledge graph management system for the smelting industry is characterized by: A method for managing a knowledge graph for a smelting industry according to any one of claims 1 to 8, comprising: The first module is used to analyze the historical smelting records and determine a number of smelting status analysis data groups, which include a number of smelting process performance factors and status interpretation data; The second module is used to extract condition keywords and interpretation keywords from the smelting condition analysis data group using semantic analysis technology, determine the condition parameters corresponding to the condition keywords, and determine the semantic pointing relationship of the interpretation keywords; The third module is used to construct an index structure of the industrial knowledge graph based on the condition keywords and corresponding condition parameters of the smelting condition analysis data group, associate the index structure with the corresponding condition interpretation data, classify the index structure based on the equality of the interpretation keywords of the smelting condition analysis data group, and classify the index branches of the index structure; The fourth module is used to determine the expandable range of each status parameter of the index branch of the same category, and then determine the fuzzy characteristics of the index branch.

Images